ksb.csle.didentification.verification.check
The entropy L-diversity constraint calculates the entropy of sensitive attributes while considering their distributions in an equivalence class.
The entropy L-diversity constraint calculates the entropy of sensitive attributes while considering their distributions in an equivalence class. A table is Entropy l-diverse if for every equivalence class E -sigma_{s \in S}p(E,s)log(p(E,s)) >= log(l) where p(E,s) is the fraction of tuples in the equivalence class E with sensitive attribute value equal to s.
Boolean return true when satisfying privacy policy
The common L-diversity method just checks whether the number of sensitive attributes is greater than given L-constraints.
The common L-diversity method just checks whether the number of sensitive attributes is greater than given L-constraints. Generally, an equivalence class is l-diverse if contains at least 'l' well-represented values for the sensitive attribute. A table is l-diverse if every equivalence is l-diverse
The anonymized dataframe
Double return the l-diversity value
Checks the anonymized dataframe satisfies the given l-Diversity constraint.
Checks the anonymized dataframe satisfies the given l-Diversity constraint.
The anonymized dataframe
the given l-diversity constraint
Boolean return true if satisfying the given l-diversity constraint
This class checks whether the anonymized data satisfies the entropy L-diversity constraint.Note that this class checks the l-diversity value in an single equivalence class, not the dataframe.